Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Justinmendezai/The-Adam-Repo --skill context-primergit clone --depth 1 https://github.com/Justinmendezai/The-Adam-RepoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/justinmendezai/the-adam-repo/context-primer)<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/context-primer"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/context-primer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/justinmendezai/the-adam-repo/context-primer"><img src="https://agentmods.dev/badge/skills/justinmendezai/the-adam-repo/context-primer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.02109 |
| Opus 5 | $0.00039 | $0.01055 |
| Sonnet 5 | $0.00016 | $0.00422 |
| Haiku 4.5 | $0.00008 | $0.00211 |
Grade A, and why
context-primer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
context-primer
The token-budget escape hatch. When the orchestrator is getting heavy, dump everything the next agent needs to resume the build into a single primer file. The next session reads only the primer, not your full transcript.
Canonical handoff for Adam: if agent-control/next-orchestrator-brief.md exists, treat it as the source of truth for “what to do next.” This skill still writes scratch/handoff/primer-*.md as an audit trail — that primer must not contradict the brief.
After writing the primer, update agent-control/next-orchestrator-brief.md (or add a prominent pointer at the top of the primer: "Sync this content into agent-control/next-orchestrator-brief.md via copy or run session-steward").
When to run
- Token usage at ~50–60% of capacity.
- About to hand off to a different model or person.
- About to wrap for the day on a multi-day build.
- After
e2e-acceptance— capture the final state for posterity.
When to compact (decision table)
The 50–60% threshold tells you when you may; this table tells you whether you should. Compact at logical phase boundaries, not mid-task.
| Phase transition | Compact? | Why |
|---|---|---|
| Research/intake → plan | Yes | Research context is bulky; the plan is the distilled output. |
| Plan → build (first dispatch) | Yes | The plan lives in plan/ and slice-status.md; free context for dispatch and review. |
| Mid-implementation review of one slice | No | You lose file paths, branch names, and partial dispatch state. Finish the wave first. |
| After a failed approach / abandoned dispatch | Yes | Clear the dead-end reasoning before trying a new path. |
| Build → e2e-acceptance | Maybe | Keep if the acceptance walk references slices you just reviewed; compact if switching focus. |
| Between bounded orchestrator cycles | Yes | Hand the next cycle a clean brief via session-steward. |
What survives a compaction
Compact with confidence by knowing what persists versus what is lost. Anything in the "Lost" column must be written to disk before you compact.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 181 lines · 79 tokens per session scan A 5ecb9f9a00f7
context-primer is a skill published in the GitHub repository Justinmendezai/The-Adam-Repo (12 stars, last pushed 18d ago), licensed Apache-2.0. It adds 79 tokens to every session and 2,109 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.